Install
$ dsh plugin --profile web add [email protected]Plugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Injects token-bounded, prefix-cache-friendly Hot Memory directly into the system prompt
- Provides agent tools (memoir_record, memoir_update, memoir_read) for memory recording and retrieval
- Features BM25 search and LRU query caching supporting Chinese, English, identifiers, and multilingual paths
- Prompts top-level agents for distillation upon completing productive working turns
- Includes a native bilingual Web GUI with dedicated session views, settings, and diagnostics
Useful For
- Maintaining ongoing project context across multiple independent DeepSeek Harness agent sessions
- Recalling previous architectural decisions, coding patterns, and debugging lessons without external embeddings
- Auditing and governing agent memory via an integrated Web UI with pinning, archiving, and deduplication
Who It Fits
- Developers using DeepSeek Harness who require persistent project memory across multi-turn sessions
- Teams seeking local-first, zero-cloud memory management without vector DB overhead
Documented Limitations
- Does not provide vector-based semantic search; retrieval is term-based (BM25)
- Requires specific DeepSeek Harness host versions (>=0.2.0-rc.1 <0.3.0-0 or >=0.2.1-alpha.1 <0.2.1 for version 0.9.2)
- Snapshot frozen in an active session does not dynamically rewrite hot memory mid-session to protect KV cache
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 32 development, 3 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as Apache-2.0.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- Qinling-Melon-Farmers/dsh-memoir
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- d658187 · 2026-10-16
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 35GitHub stars
- Forks
- 3
- Open issues
- 1
- Last commit
- 2026-10-09
- Last release
- 2026-10-09
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Lingshu long-term auditable memory system and cognitive graph for DeepSeek Harness.
View plugin →Persistent semantic memory layer for DeepSeek Harness backed by Markdown and Milvus.
View plugin →Composable, view-based layered memory bundle for DeepSeek Harness with pluggable providers and strategies.
View plugin →Comprehensive long-term memory, self-evolution, skills, task management, and multi-agent dispatch bundle for DeepSeek Harness.
View plugin →